RamonYeung

"""Short and sweet LSTM implementation in Tensorflow.

Motivation:
When Tensorflow was released, adding RNNs was a bit of a hack - it required
building separate graphs for every number of timesteps and was a bit obscure
to use. Since then TF devs added things like `dynamic_rnn`, `scan` and `map_fn`.
Currently the APIs are decent, but all the tutorials that I am aware of are not
making the best use of the new APIs.

Advantages of this implementation:

RamonYeung

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

RamonYeung

一行 Python 实现树

使用 Python 内置的 defaultdict，我们可以很容易的定义一个树形数据结构：

def tree(): return defaultdict(tree)

就是这样！

RamonYeung

# Recall that, in regex, we use [\u4e00-\u9fa5] to match chinese characters.

start = int("4e00", 16)
end = int("9fa5", 16)

for i in range(start, end + 1):
    uni = r"\u" + hex(i)[2:]
    result = uni.encode("utf-8").decode("unicode_escape")
    print(result)

RamonYeung

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

RamonYeung

import requests
import re
from urllib.request import urlopen
import multiprocessing as mp
import os

def process(pair):
    idx, title = pair
    idx = '0' * (4 - len(idx)) + idx
    for word in keywords:

RamonYeung

#!/usr/bin/python

import sys
import json

if len(sys.argv) != 3:
  sys.exit("Usage: %s <gold_file> <result_file>" % sys.argv[0])

"""load the answers to a list"""
def loadAnswers(filename):

RamonYeung

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np

RamonYeung

# Here is a list of stop words in English and it is taken from nltk.corpus.stopwords
# requirements: NLTK==3.2.4

stop_words = ['a', 'about', 'above', 'after', 'again', 'against', 'ain', 'all', 'am', 'an', 'and', 'any', 'are', 'aren', "aren't", 'as', 'at', 
              'be', 'because', 'been', 'before', 'being', 'below', 'between', 'both', 'but', 'by', 
              'can', 'couldn', "couldn't", 
              'd', 'did', 'didn', "didn't", 'do', 'does', 'doesn', "doesn't", 'doing', 'don', "don't", 'down', 'during',
              'each', 
              'few', 'for', 'from', 'further', 
              'had', 'hadn', "hadn't", 'has', 'hasn', "hasn't", 'have', 'haven', "haven't", 'having', 'he', 'her', 'here', 'hers', 'herself', 'him', 'himself', 'his', 'how',

RamonYeung

# coding: utf-8

import logging
import re
from collections import Counter

import numpy as np
import torch
from sklearn.datasets import fetch_20newsgroups
from torch.autograd import Variable